© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 3148
    Prev
    Next
    INDEX
    Explanations

    у

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sul
    -0.09
     Nobel
    -0.08
     faith
    -0.07
    _led
    -0.07
    114
    -0.07
    ensa
    -0.07
    ici
    -0.07
    Shapes
    -0.07
     �
    -0.07
     Bau
    -0.07
    POSITIVE LOGITS
     vale
    0.08
     sleeve
    0.07
     சேர்ந்த
    0.07
     opis
    0.07
     determ
    0.07
    _IND
    0.07
     poly
    0.07
     polys
    0.07
     appendix
    0.07
    태
    0.07
    Activations Density 0.003%

    No Known Activations